© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21446
    Prev
    Next
    INDEX
    Explanations

    extinct animals and diseases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èµĶ
    -0.09
    èĿĮ
    -0.09
    èĿ
    -0.09
    åĪĨè£Ĥ
    -0.09
    线索
    -0.09
    æī«
    -0.09
    æµ·åºķ
    -0.09
    çł¥
    -0.09
     cater
    -0.09
    综
    -0.08
    POSITIVE LOGITS
    çĮİ
    0.10
     buffalo
    0.10
    è·µ
    0.10
    åĬ¨çī©
    0.09
    龸çİĭ
    0.09
    åĴĨ
    0.09
    弩
    0.09
    èĻİ
    0.09
    æIJı
    0.08
    åĮ¹
    0.08
    Activations Density 0.132%

    No Known Activations